This article presents a cross-sectional model for forecasting research output across the Australian university system. It builds upon an existing literature that focuses either on institutional comparisons or studies of specific subjects, by providing discipline-specific results across all of the 10 major disciplinary areas as defined by Australia's Department of Education, Science and Training. The model draws upon four (highly significant) discipline-specific explanatory variables; staff size, research expenditure, PhD completions and student-staff ratios to predict the output of refereed articles.